Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to agreements or permissions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of intense emotional experiences or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     funded
    -0.70
     div
    -0.66
     directly
    -0.65
     allied
    -0.63
     actively
    -0.63
     officially
    -0.63
     currently
    -0.63
     targeting
    -0.62
     targeted
    -0.62
    senal
    -0.62
    POSITIVE LOGITS
    SPONSORED
    1.21
    Newsletter
    1.20
    Advertisement
    1.17
    Then
    1.12
    Eventually
    1.11
    Suddenly
    1.11
    Years
    1.01
    Later
    0.97
    Around
    0.97
    Phot
    0.97
    Act Density 0.737%

    No Known Activations